4 papers
Population Fidelity: Evaluating Population Representativeness in LLMs
Neemias B. da Silva, Martin Lukk, Ali Sutani +5
Large language models (LLMs) show considerable potential in simulating human attitudes and preferences. Prior work finds that LLM-generated responses can compress the range of atti…
Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory
Matt Ratto, Abhishek Moturu, Daniel Silver
As AI systems are deployed across increasingly diverse social contexts, alignment can no longer be framed as the optimization of a single, unified set of values. Instead, systems m…
Persona Prompting in Multimodal Urban Perception: Descriptive Convergence and Interpretive Variation
Neemias da Silva, Matt Ratto, Myriam Delgado +3
This study examines how persona prompting shapes language generated by two multimodal large language models in urban perception, a setting for examining subjective interpretations…
A Fully Generative Motivational Interviewing Counsellor Chatbot for Moving Smokers Towards the Decision to Quit
Zafarullah Mahmood, Soliman Ali, Jiading Zhu +12
The conversational capabilities of Large Language Models (LLMs) suggest that they may be able to perform as automated talk therapists. It is crucial to know if these systems would…